Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2922 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.3953. Min Act: -0.1700

Data Index: 8775851 (Open Web Text)

Max Activating Token Index: 475

Text #1

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.1815. Min Act: -0.1700

Data Index: 2557332 (Open Web Text)

Max Activating Token Index: 451

Text #2

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.1692. Min Act: -0.1700

Data Index: 7111664 (Open Web Text)

Max Activating Token Index: 708

Text #3

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.1963. Min Act: -0.1700

Data Index: 1873940 (Open Web Text)

Max Activating Token Index: 422

Text #4

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.1612. Min Act: -0.1700

Data Index: 5331296 (Open Web Text)

Max Activating Token Index: 706

Text #5

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.1427. Min Act: -0.1700

Data Index: 5477932 (Open Web Text)

Max Activating Token Index: 956

Text #6

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.0884. Min Act: -0.1700

Data Index: 8526463 (Open Web Text)

Max Activating Token Index: 988

Text #7

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.0832. Min Act: -0.1700

Data Index: 5123109 (Open Web Text)

Max Activating Token Index: 199

Text #8

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.1236. Min Act: -0.1700

Data Index: 4312034 (Open Web Text)

Max Activating Token Index: 910

Text #9

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.0494. Min Act: -0.1700

Data Index: 4261510 (Open Web Text)

Max Activating Token Index: 662

Text #10

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.0614. Min Act: -0.1700

Data Index: 8024785 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.3953. Min Range: -4.3953

Max Act: 3.9855. Min Act: -0.1700

Data Index: 1802529 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.0037. Min Act: -0.1700

Data Index: 396829 (Open Web Text)

Max Activating Token Index: 551

Text #13

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.0138. Min Act: -0.1700

Data Index: 6674379 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.0090. Min Act: -0.1700

Data Index: 6607666 (Open Web Text)

Max Activating Token Index: 918

Text #15

Max Range: 4.3953. Min Range: -4.3953

Max Act: 3.9605. Min Act: -0.1700

Data Index: 3327846 (Open Web Text)

Max Activating Token Index: 881

Text #16

Max Range: 4.3953. Min Range: -4.3953

Max Act: 4.0035. Min Act: -0.1700

Data Index: 442324 (Open Web Text)

Max Activating Token Index: 419

Text #17

Max Range: 4.3953. Min Range: -4.3953

Max Act: 3.9776. Min Act: -0.1700

Data Index: 3808019 (Open Web Text)

Max Activating Token Index: 906

Text #18

Max Range: 4.3953. Min Range: -4.3953

Max Act: 3.9398. Min Act: -0.1700

Data Index: 7755277 (Open Web Text)

Max Activating Token Index: 598

Text #19

Max Range: 4.3953. Min Range: -4.3953

Max Act: 3.9549. Min Act: -0.1700

Data Index: 7956192 (Open Web Text)

Max Activating Token Index: 866